Apparatus and methods for predicting a semiconductor parameter across an area of a wafer
Apparatus and methods are provided for predicting a plurality of unknown parameter values (e.g. overlay error or critical dimension) using a plurality of known parameter values. In one embodiment, the method involves training a neural network to predict the plurality of parameter values. In other embodiments, the prediction process does not depend on an optical property of a photolithography tool. Such predictions may be used to determine wafer lot disposition.
1. A method of predicting a plurality of parameter values distributed over at least a portion of a wafer, the method comprising:
providing a plurality of known parameter values measured from a plurality of targets at specific measurement locations on the wafer;
training a neural network using the measured, known parameter values so that the trained neural network is configured to predict a plurality of predicted parameter values such that a subset of the predicted parameter values which correspond to the specific measurement locations are within a predefined error function of the corresponding measured, known parameter values;
using the trained neural network to predict the predicted parameter values at the plurality of locations distributed across at least a portion of the wafer; and
determining whether the wafer passes or fails based on the predicted parameter values predicted by the trained neural network.
2. A method as recited in claim 1 , wherein the predicted parameter values are distributed across the entire wafer or across a field of the wafer.
3. A method as recited in claim 1 , wherein the predicted parameter values comprise a plurality of overlay error values or critical dimension values.
4. A method as recited in claim 1 , wherein training the neural network and using the trained neural network includes inputting at least one target metric of at least one of the targets of the wafer into the neural network and the trained neural network.
5. A method as recited in claim 1 , wherein training the neural network and using the trained neural network includes inputting at least one noise metric that quantifies a background characteristic of the at least one target of the wafer, at least one systematic metric of the at least one target of the wafer, an alignment metric from a photolithography tool into the neural network and the trained neural network, and at least one process metric that characterizes a property of the wafer into the neural network and the trained neural network.
6. A method comprising:
providing a plurality of known parameter values measured from a wafer or obtained from a process for forming a wafer; and
using a trained neural network model to predict a plurality of unknown parameter values based on the known parameter values.
7. A method as recited in claim 6 , wherein using a trained neural network model is performed without use of a model of the photolithography tool and without depending on an optical property of a photolithography tool.
8. A method as recited in claim 7 , wherein the optical property includes a lens aberration characteristic.
9. An apparatus for predicting a plurality of parameter values distributed over at least a portion of a wafer, the apparatus comprising:
one or more processors;
one or more memory, wherein at least one of the processors and memory are configured for:
providing a plurality of known parameter values measured from a plurality of targets at specific measurement locations on the wafer;
training a neural network using the measured, known parameter values so that the trained neural network is configured to predict a plurality of predicted parameter values such that a subset of the predicted parameter values which correspond to the specific measurement locations are within a predefined error function of the corresponding measured, known parameter values;
using the trained neural network to predict the predicted parameter values at the plurality of locations distributed across at least a portion of the wafer; and
determining whether the wafer passes or fails based on the predicted parameter values predicted by the trained neural network.
10. An apparatus as recited in claim 9 , wherein the predicted parameter values are distributed across the entire wafer or across a field of the wafer.
11. An apparatus as recited in claim 9 , wherein the predicted parameter values comprise a plurality of overlay error values or critical dimension values.
12. An apparatus as recited in claim 9 , wherein training the neural network and using the trained neural network includes inputting at least one target metric of at least one of the targets of the wafer into the neural network and the trained neural network.
13. An apparatus as recited in claim 9 , wherein training the neural network and using the trained neural network includes inputting at least one noise metric that quantifies a background characteristic of the at least one target of the wafer, at least one systematic metric of the at least one target of the wafer, an alignment metric from a photolithography tool into the neural network and the trained neural network, and at least one process metric that characterizes a property of the wafer into the neural network and the trained neural network.
14. An apparatus comprising:
one or more processors;
one or more memory, wherein at least one of the processors and memory are configured for:
providing a plurality of known parameter values measured from a wafer or obtained from a process for forming a wafer; and
using a trained neural network model to predict a plurality of unknown parameter values based on the known parameter values.
15. An apparatus as recited in claim 14 , wherein using a trained neural network model is performed without use of a model of the photolithography tool and without depending on an optical property of a photolithography tool.
16. An apparatus as recited in claim 14 , wherein the optical property includes a lens aberration characteristic.
17. An apparatus as recited in claim 14 , wherein the known parameter values are obtained from a process for forming a wafer.
18. An apparatus as recited in claim 17 , wherein the known parameter values comprise one or more of the following values: post exposure bake (PEB) temperature, PEB time, bottom anti-reflective coating (BARC) thickness, development time, dose, focus, or scan direction values from a photolithography tool for forming a wafer.
19. An apparatus as recited in claim 14 , wherein the known parameter values characterize a property of the wafer.
20. An apparatus as recited in claim 19 , wherein the known parameter values comprise one or more of the following: overlay, critical dimension, side wall angle, photoresist thickness, or wafer flatness values.
21. An apparatus as recited in claim 19 , wherein the unknown parameter values comprise overlay or critical dimension values.
22. A method as recited in claim 6 , wherein the known parameter values are obtained from a process for forming a wafer.
23. A method as recited in claim 22 , wherein the known parameter values comprise one or more of the following values: post exposure bake (PEB) temperature, PEB time, bottom anti-reflective coating (BARC) thickness, development time, dose, focus, or scan direction values from a photolithography tool for forming a wafer.
24. A method as recited in claim 6 , wherein the known parameter values characterize a property of the wafer.
25. A method as recited in claim 24 , wherein the known parameter values comprise one or more of the following: overlay, critical dimension, side wall angle, photoresist thickness, or wafer flatness values.
26. A method as recited in claim 6 , wherein the unknown parameter values comprise overlay or critical dimension values.